Yun Liu, Peng-Tao Jiang, Vahan Petrosyan, Shi-Jie Li, Jiawang Bian, Le Zhang, Ming-Ming Cheng
In IJCAI, vol. 864, p. 870. 2018
Publication year: 2018

Image segmentation has been explored for many years and still remains a crucial vision problem. Some efficient or accurate segmentation algorithms have been widely used in many vision applications. However, it is difficult to design a both efficient and accurate image segmenter. In this paper, we propose a novel method called DEL (deep embed- ding learning) which can efficiently transform su- perpixels into image segmentation. Starting with the SLIC superpixels, we train a fully convolutional network to learn the feature embedding space for each superpixel. The learned feature embedding corresponds to a similarity measure that measures the similarity between two adjacent superpixels. With the deep similarities, we can directly merge the superpixels into large segments. The evaluation results on BSDS500 and PASCAL Context demon- strate that our approach achieves a good trade- off between efficiency and effectiveness. Specifi- cally, our DEL algorithm can achieve comparable segments when compared with MCG but is much faster than it, i.e. 11.4fps vs. 0.07fps. Project page is available at


邮箱地址不会被公开。 必填项已用*标注